Laying Anchors: Semantically Priming Numerals in Language Modeling
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913461049491456 |
|---|---|
| author | Sharma, Mandar Taware, Rutuja Murlidhar Koirala, Pravesh Muralidhar, Nikhil Ramakrishnan, Naren |
| author_facet | Sharma, Mandar Taware, Rutuja Murlidhar Koirala, Pravesh Muralidhar, Nikhil Ramakrishnan, Naren |
| contents | Off-the-shelf pre-trained language models have become the de facto standard in NLP pipelines for a multitude of downstream tasks. However, the inability of these models to properly encode numerals limits their performance on tasks requiring numeric comprehension. We introduce strategies to semantically prime numerals in any corpus by generating anchors governed by the distribution of numerals in said corpus, thereby enabling mathematically grounded representations of these numeral tokens. We establish the superiority of our proposed techniques through evaluation on a range of numeracy tasks for both in-domain (seen) and out-domain (unseen) numerals. Further, we expand our empirical evaluations to numerals ranging from 1 to 10 billion, a significantly broader range compared to previous studies of the same nature, and we demonstrate significant improvements in the mathematical grounding of our learned embeddings. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_01536 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Laying Anchors: Semantically Priming Numerals in Language Modeling Sharma, Mandar Taware, Rutuja Murlidhar Koirala, Pravesh Muralidhar, Nikhil Ramakrishnan, Naren Computation and Language Artificial Intelligence Machine Learning Off-the-shelf pre-trained language models have become the de facto standard in NLP pipelines for a multitude of downstream tasks. However, the inability of these models to properly encode numerals limits their performance on tasks requiring numeric comprehension. We introduce strategies to semantically prime numerals in any corpus by generating anchors governed by the distribution of numerals in said corpus, thereby enabling mathematically grounded representations of these numeral tokens. We establish the superiority of our proposed techniques through evaluation on a range of numeracy tasks for both in-domain (seen) and out-domain (unseen) numerals. Further, we expand our empirical evaluations to numerals ranging from 1 to 10 billion, a significantly broader range compared to previous studies of the same nature, and we demonstrate significant improvements in the mathematical grounding of our learned embeddings. |
| title | Laying Anchors: Semantically Priming Numerals in Language Modeling |
| topic | Computation and Language Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2404.01536 |